web monitoring

zie https://uptimerobot.com/, credentials in pass

server monitoring

handmatig

potentiele punten om te monitoren:

linux version:
- lsb_release -d
CPU usage:
- top -bn1 | grep Cpu
- greenhost tab Grafieken
ram usage
- free | grep Mem | awk '{print $3/$2}'
- free -h
- top -bn1 | grep 'MiB Mem'
bandwidth: nethogs
ping speeds van servers
- ping -c 1 $SERVER | grep 'time='

disk usage

check allocated: lsblk
check usage: df -h | grep 'G'
check where this went:
- folders: sudo du --max-depth=1 / | sort -n -r
- files: ls -lhS / | head -n 10
- docker: sudo docker images | sort -k7 -h
  - reclaim docker space not part of running containers: sudo docker system prune -a
extend: sudo xfs_growfs /

batch

servers=(
    "vergadering.bij1.net"
    "static.bij1.net"
    "wp.bij1.net"
    "wp-staging.bij1.net"
    "proxy.bij1.net"
    "stemmen.bij1.net"
    "cloud.bij1.net"
    "crm.bij1.net"
    "code.bij1.net"
    "build.bij1.net"
    "db.bij1.net"
    "db2.bij1.net"
    "ns.bij1.net"
)

run_everywhere () {
    for server in $servers; do
        echo $server
        ssh $server $@
    done
}

# linux version
run_everywhere "lsb_release -d"
# CPU usage
run_everywhere "top -bn1 | grep Cpu"
# RAM usage
run_everywhere "free | grep Mem | awk '{print \$3/\$2}'"
# disk usage
run_everywhere "df -h | grep '/dev/'"
# failed services
run_everywhere "sudo systemctl | grep failed"
# periodic jobs
run_everywhere "sudo crontab -l | grep -v -E '^#'"
# update
run_everywhere "sudo apt-get update -y"

nextcloud

https://cloud.bij1.org/settings/admin/serverinfo

docker

docker compose

docker-compose logs

email usage

curl -X GET -H "Content-Type: application/json" -H "Authorization: Bearer ${TRANSIP_TOKEN}" "https://api.transip.nl/v6/email/bij1.org/mailboxes" 2>/dev/null | jq '.mailboxes | map_values({used: (.usedDiskSpace / .availableDiskSpace), name: .localPart }) | sort_by(.used)'